most citedAn End-to-End Mispronunciation Detection System for L2 English Speech Leveraging Novel Anti-Phone Modeling

1 citations · 1 across the 3 of their papers we have counts for

collaborators
Showing cs.CLShow all

1 paper · 1 filter

cs.CL2026

ASPIRin: Action Space Projection for Interactivity-Optimized Reinforcement Learning in Full-Duplex Speech Language Models

Chi-Yuan Hsiao, Ke-Han Lu, Yu-Kuan Fu +3

End-to-end full-duplex Speech Language Models (SLMs) require precise turn-taking for natural interaction. However, optimizing temporal dynamics via standard raw-token reinforcement…